Skip to main content
Glama

cognitive.safe_self_improve

Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rollbackNo
patch_nameYes
proposed_changesYes
target_componentYes
rollback_snapshot_idNo
simulated_regression_failNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden, but it only calls the operation 'safe' and mentions abstract guards. It does not disclose whether changes are actually applied, whether rollback is required, what happens when oracle verification fails, or what the output describes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence with no wasted words, and the core purpose is front-loaded. However, it is so compressed that it leans toward cryptic rather than clearly structured for a complex tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, a nested proposed_changes object, and no annotations, one sentence is insufficient. The description does not explain what target components exist, how patch proposals are validated, what rollback does, or how regression failures are simulated, so the agent lacks enough context to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description names none of the six parameters. It vaguely maps to 'modifications' but gives no meaning for target_component, patch_name, proposed_changes, rollback, rollback_snapshot_id, or simulated_regression_fail, leaving the agent to infer semantics from titles alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb-resource pairing: 'propose modifications' plus a clear safety framing ('guarded by immutable verification oracles and anchor regressions'). This helps distinguish it from generic self-improvement or planning siblings, though it does not define those guardrails concretely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives such as cognitive.learn_from_mistake, cognitive.record_experience, or cognitive.inspect_self_model. The word 'safe' implies a context, but there is no stated trigger, precondition, or exclusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources